AI Threat Alert

AI Security Threat Feed

Latest CVEs affecting AI/ML systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers. Vulnerabilities are tracked from NVD, GitHub Advisory, CISA KEV, MITRE ATLAS, and enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings to ISO 42001, EU AI Act, NIST AI RMF, and OWASP LLM Top 10. Updated continuously as new CVEs are published.

Sources
Each CVE is enriched with
  • CVSS severity
  • EPSS exploit probability
  • Exploitation confidence
  • AI-component classification
  • Compliance mappings
4,307

AI/ML CVEs Tracked

533

Critical

95

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 1961 results — Active exploitation
HIGHEXPLOIT AVAIL

Flowise: CORS wildcard enables file read and data theft

CVE-2024-36421
7.5
EPSS 8.5%
Data ExtractionAuth BypassData LeakageAgentFramework
flowiseCWE-3465 ATLAS
HIGHEXPLOIT AVAILSCANNER

Flowise: unauthenticated arbitrary file read via API

CVE-2024-36420
7.5
EPSS 1.8%
Data ExtractionAuth BypassData LeakageFrameworkAPIAgent
flowiseCWE-746 ATLAS
LOWEXPLOIT AVAIL

lollms-webui: CSRF allows unauthorized AI service install

CVE-2024-4839
3.3
EPSS 0.2%
Supply ChainAuth BypassInferenceFramework
lollms-webui4 ATLAS
MEDIUMEXPLOIT AVAILSCANNER

Gradio: open redirect enables phishing against ML users

CVE-2024-4940
6.1
EPSS 1.0%
Social EngineeringPrivacy ViolationFrameworkInference
gradio7355 ATLAS
HIGHEXPLOIT AVAIL

LangChain: Python REPL code execution without opt-in

CVE-2024-38459
7.8
EPSS 0.2%
Code ExecutionPrompt InjectionData ExtractionFrameworkAgent
langchain-experimental3.2K5 ATLAS
CRITICALEXPLOIT AVAILSCANNER

Langflow: unauthenticated RCE via custom component API

CVE-2024-37014
9.8
EPSS 63.7%
Code ExecutionAuth BypassSupply ChainFrameworkAgentAPI
langflowCWE-945 ATLAS
HIGHEXPLOIT AVAIL

ONNX: path traversal in model download enables RCE

CVE-2024-5187
8.8
EPSS 1.2%
Supply ChainCode ExecutionFrameworkModel
onnxPatch: 1.16.2CWE-221.1K4 ATLAS
MEDIUMEXPLOIT AVAIL

langchain-community: DoS via recursive sitemap loop

CVE-2024-2965
4.2
EPSS 0.3%
DoSSupply ChainFrameworkRAG
langchainPatch: 0.2.5CWE-4003.2K3 ATLAS
MEDIUMEXPLOIT AVAIL

scikit-learn: TfidfVectorizer leaks training data tokens

CVE-2024-5206
4.7
EPSS 0.2%
Data LeakageData ExtractionPrivacy ViolationFrameworkTraining Data
scikit-learnCWE-92232.7K5 ATLAS
HIGHEXPLOIT AVAIL

litellm: arbitrary file deletion via audio endpoint

CVE-2024-4888
8.1
EPSS 0.6%
Auth BypassDoSFrameworkAPI
litellm63 ATLAS
CRITICALEXPLOIT AVAILSCANNER

ChuanhuChatGPT: path traversal exposes LLM API keys

CVE-2024-3234
9.8
EPSS 3.8%
Data ExtractionAuth BypassData LeakageFrameworkAPI
chuanhuchatgpt5 ATLAS
MEDIUMEXPLOIT AVAIL

MLflow: URL encoding bypass enables model poisoning

CVE-2024-3099
5.4
EPSS 0.4%
Model PoisoningDoSFrameworkModel
mlflow6955 ATLAS
HIGHEXPLOIT AVAIL

LangChain: SSRF in Web Retriever exposes cloud metadata

CVE-2024-3095
7.7
EPSS 0.7%
Data ExtractionAuth BypassFrameworkAgentRAG
langchain3.2K4 ATLAS
HIGHEXPLOIT AVAILSCANNER

MLflow: URI fragment LFI exposes arbitrary files

CVE-2024-2928
7.5
EPSS 21.8%
Data ExtractionSupply ChainFrameworkModelTraining Data
mlflowCWE-226956 ATLAS
HIGHEXPLOIT AVAIL

MLflow: path traversal enables RCE via dataset loading

CVE-2024-0520
8.8
EPSS 2.4%
Code ExecutionSupply ChainData LeakageFrameworkTraining Data
mlflow6955 ATLAS
CRITICALEXPLOIT AVAIL

pytorch-lightning: RCE via deepdiff Delta deserialization

CVE-2024-5452
9.8
EPSS 26.8%
Code ExecutionSupply ChainFramework
pytorch_lightningCWE-91326.1K5 ATLAS
HIGHEXPLOIT AVAIL

Gradio: LFI via JSON path key exposes server files

CVE-2024-4941
7.5
EPSS 0.8%
Data ExtractionData LeakageFrameworkInference
gradio7354 ATLAS
HIGHKEVSCANNER

Gradio: SSRF exposes internal network and cloud metadata

CVE-2024-4325
8.6
EPSS 37.1%
Data ExtractionAuth BypassFrameworkInference
gradio7354 ATLAS
UNKNOWNEXPLOIT AVAIL

Gradio: secrets exfiltration via unsafe fork PR workflow

CVE-2024-4254
--
EPSS 0.5%
Supply ChainData ExtractionAuth BypassFrameworkModel
gradio7355 ATLAS
HIGHEXPLOIT AVAIL

MLflow: RCE via malicious MLproject file execution

CVE-2024-37061
8.8
EPSS 0.9%
Code ExecutionSupply ChainFrameworkTraining Data
mlflowCWE-946956 ATLAS

Frequently asked questions

What is an AI security threat feed?

An AI security threat feed is a continuously updated stream of vulnerabilities (CVEs) affecting AI and machine-learning systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — filtered out of the broader CVE firehose and enriched for relevance.

Which sources are the AI CVEs tracked from?

CVEs are tracked from NVD, GitHub Advisory, CISA KEV, and MITRE ATLAS, then enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings.

What AI systems do these vulnerabilities affect?

Coverage spans LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — the components most security teams now run in production.

How often is the AI threat feed updated?

The feed updates continuously as new CVEs are published and enriched, so the most recent AI/ML vulnerabilities appear at the top.

Is the AI security feed free?

Yes — the public feed is free to browse. A Pro subscription adds breaking alerts, MITRE ATLAS mappings, compliance reports (ISO 42001, EU AI Act), and full CISO analysis.

Need deeper analysis?

Get ATLAS technique mappings, compliance reports (ISO 42001, EU AI Act), breaking alerts, and full CISO analysis with a Pro subscription.

Start 14-Day Free Trial